What is odoo-security-audit?

A security audit guide for Odoo Python, JavaScript, XML, and QWeb code. It reports vulnerabilities with severity, affected lines, attack paths, and suggested fixes, but does not apply the fixes.

Use it to audit Odoo modules, controllers, model methods, templates, and access-control files for exploitable security problems.

It helps teams find security weaknesses such as injection, cross-site scripting, and missing access controls before deployment. The report gives developers concrete information for fixing each issue.

odoo-security-audit — Skill for Claude Code by Viindoo/odoo-mcp-client

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add Viindoo/odoo-mcp-client

Claude Code

/plugin install odoo-ai-agents

Made for: Claude Code.

Or install odoo-ai-agents, the plugin that ships this one along with the rest of its 50 skills, 8 commands, 23 agents, 8 hooks, 3 MCP servers.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/viindoo/odoo-mcp-client/odoo-security-audit/github.svg)](https://agentmods.dev/skills/viindoo/odoo-mcp-client/odoo-security-audit)

Your own site

<a href="https://agentmods.dev/skills/viindoo/odoo-mcp-client/odoo-security-audit"><img src="https://agentmods.dev/badge/skills/viindoo/odoo-mcp-client/odoo-security-audit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/viindoo/odoo-mcp-client/odoo-security-audit"><img src="https://agentmods.dev/badge/skills/viindoo/odoo-mcp-client/odoo-security-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,348 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00023	$0.02348
Opus 5.5	$0.00009	$0.00939
Sonnet 5.5	$0.00005	$0.00470
Haiku 4.5	$0.00002	$0.00235

Measured yesterday against content hash b5040b7fc63a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

odoo-security-audit scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

Security-only static audit of Odoo code: injection, XSS, access, sudo model: inherit

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

plugins/odoo-ai-agents/skills/odoo-security-audit/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Security-focused Developer / Tech Lead auditing Odoo source code with OSM-grounded analysis.

Out of Scope

Writing fixes - route to odoo-coding
Pre-upgrade deprecation sweep - route to odoo-deprecation-audit
Live render or runtime error verification - route to odoo-debug
Performance / N+1 / convention review - route to odoo-code-review
Override safety - route to odoo-override-finding

When to use

Invoke whenever:

Code is shared (pasted, file path referenced, or available from a prior step) and security, safety, or deployment readiness is the concern
A PR touches controllers, model methods with sudo(), QWeb templates with t-raw, or CSV access files
A module is being deployed or reviewed for the first time with no prior security audit

Reactive mode (dispatched by odoo-debug). When odoo-debug routes a runtime security symptom here (observed leak, unexpected AccessError, apparent injection - with reproduction + version), root-cause THAT symptom per ${CLAUDE_PLUGIN_ROOT}/skills/_shared/debug-method.md and emit the same graded report. A direct invocation with no specific symptom stays a proactive audit.

Diff-scope mode (optional)

Default (no SCOPE_FILES/CHANGED_SET supplied): whole-module output, UNCHANGED - a standalone invocation of this skill is unaffected.

When a caller (e.g. odoo-code-reviewer's own Audit escalation step) briefs this skill with SCOPE_FILES/CHANGED_SET - the diff's touched files - restrict authoritative findings to those files plus their direct callers (blast-radius: reverse-dependency lookup, or a local grep for call-sites when OSM is unavailable). Report any finding outside that scope (pre-existing code) in a separate "Pre-existing / blast-radius" section of the output - never silently dropped, never merged into the diff-scoped findings.

Findings are graded on the shared scale defined in ${CLAUDE_PLUGIN_ROOT}/snippets/review-severity-rubric.md - one severity scale governs the whole review-plus-audit pipeline.

Read the full file on GitHub · 126 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/vulnerability-taxonomy.md 5.3 KB

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday Changed b5040b7fc63a
17d ago Changed · -2 tokens per session e1d1db9f78e3
24d ago Changed 3600ad385a02
1mo ago Changed cda0d5ea430d
1mo ago Changed · -10 lines · -215 tokens per session ad51ccccd773
1mo ago Changed 46282b339e63
2mo ago First seen · 136 lines · 240 tokens per session scan A 59f777050b3e

Subscribe to this mod's changes

odoo-security-audit is a skill published in the GitHub repository Viindoo/odoo-mcp-client (9 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 2,348 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.